docling 2.5.0__py3-none-any.whl → 2.5.1__py3-none-any.whl

docling/backend/msword_backend.py

@@ -130,7 +130,6 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
     def walk_linear(self, body, docx_obj, doc) -> DoclingDocument:
         for element in body:
             tag_name = etree.QName(element).localname
-
             # Check for Inline Images (drawings or blip elements)
             found_drawing = etree.ElementBase.xpath(
                 element, ".//w:drawing", namespaces=self.xml_namespaces
@@ -201,7 +200,6 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
             label_str = ""
             label_level = 0
             if parts[0] == "Heading":
-                # print("{} - {}".format(parts[0], parts[1]))
                 label_str = parts[0]
                 label_level = self.str_to_int(parts[1], default=None)
             if parts[1] == "Heading":
@@ -217,19 +215,16 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
         if paragraph.text is None:
             # _log.warn(f"paragraph has text==None")
             return
-
         text = paragraph.text.strip()
         # if len(text)==0 # keep empty paragraphs, they seperate adjacent lists!
 
         # Common styles for bullet and numbered lists.
         # "List Bullet", "List Number", "List Paragraph"
-        # TODO: reliably identify wether list is a numbered list or not
+        # Identify wether list is a numbered list or not
         # is_numbered = "List Bullet" not in paragraph.style.name
         is_numbered = False
-
         p_style_name, p_level = self.get_label_and_level(paragraph)
         numid, ilevel = self.get_numId_and_ilvl(paragraph)
-        # print("numid: {}, ilevel: {}, text: {}".format(numid, ilevel, text))
 
         if numid == 0:
             numid = None
@@ -450,8 +445,13 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
         for row in table.rows:
             # Calculate the max number of columns
             num_cols = max(num_cols, sum(get_colspan(cell) for cell in row.cells))
-            # if row.cells:
-            #     num_cols = max(num_cols, len(row.cells))
+
+        if num_rows == 1 and num_cols == 1:
+            cell_element = table.rows[0].cells[0]
+            # In case we have a table of only 1 cell, we consider it furniture
+            # And proceed processing the content of the cell as though it's in the document body
+            self.walk_linear(cell_element._element, docx_obj, doc)
+            return
 
         # Initialize the table grid
         table_grid = [[None for _ in range(num_cols)] for _ in range(num_rows)]

{docling-2.5.0.dist-info → docling-2.5.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.5.0
+Version: 2.5.1
 Summary: SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
 Home-page: https://github.com/DS4SD/docling
 License: MIT

{docling-2.5.0.dist-info → docling-2.5.1.dist-info}/RECORD

@@ -7,7 +7,7 @@ docling/backend/docling_parse_v2_backend.py,sha256=gUr9_fwHbkj238oYQPJ9AxpjFL2jG
 docling/backend/html_backend.py,sha256=qbu1W8xoTGnXMuZPRPLq68hDbCEj6ygnpxP5gYaodAQ,15593
 docling/backend/md_backend.py,sha256=tmuSCghjor9PqKIiVieCuZ4_t5JEjZMy3cq7u3yTgyU,14032
 docling/backend/mspowerpoint_backend.py,sha256=YaVJc6RXWmM1EPTp0TzAiXpGxu6K-MZdPNsmR_64LSg,15358
-docling/backend/msword_backend.py,sha256=FAUdP74QxGKo2xMZQ4WQGYwtpIBCTJ_FG17PBpRwhxI,17230
+docling/backend/msword_backend.py,sha256=IEqGz-lUrQw0tgBly_gv_mYGC0X0iNnGhkwnDWaDtBY,17341
 docling/backend/pdf_backend.py,sha256=unnw7QiRE1VXg6Pj-eYrtnFGrp5SSYiI324OlFxyv6c,2050
 docling/backend/pypdfium2_backend.py,sha256=B4bfv-dfzlWiKTfF8LN5fto_99YBu8A2c1_XIVwRUWI,8996
 docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -38,8 +38,8 @@ docling/utils/export.py,sha256=KyGF1BVDHPFfHVXZc8vegsWlFfOgGPP2YckWpTadyI8,4694
 docling/utils/layout_utils.py,sha256=vlN0rc8i0ayRGn3WnaG-pdmqEL00KKGl2zez3Gj-hrk,32074
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
 docling/utils/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
-docling-2.5.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.5.0.dist-info/METADATA,sha256=5YYKYhn1SBIlEk7LFV4HUo5pF51PpU-ENGh_DL8udqk,6530
-docling-2.5.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling-2.5.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
-docling-2.5.0.dist-info/RECORD,,
+docling-2.5.1.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.5.1.dist-info/METADATA,sha256=qOFYM-E7GjYUIaHtwPoef22zJEWAhIZW8tlIALD17u0,6530
+docling-2.5.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling-2.5.1.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
+docling-2.5.1.dist-info/RECORD,,